INDEX

Explanations

medical terms and conditions, particularly autoimmune disorders

oai_token-act-pair · gpt-3.5-turbo

medical terminology and descriptions of health conditions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

zzle

-0.42

 slack

-0.41

 volley

-0.40

))))

-0.40

 humility

-0.39

 solicit

-0.39

 resignation

-0.39

).[

-0.38

 cheek

-0.37

RESULTS

-0.37

POSITIVE LOGITS

aceae

0.56

 geographically

0.49

apeshifter

0.48

 industrialized

0.44

erenn

0.44

 Province

0.43

 descendant

0.42

quartered

0.41

region

0.41

 UNITED

0.40

Activations Density 3.371%

medical terms and conditions, particularly autoimmune disorders

medical terminology and descriptions of health conditions

No Comments

No Known Activations